Skip to content
Log in

Data Analysis Agent System Prompt

Generates an analysis agent prompt that states its assumptions, checks data quality before concluding, refuses causal claims the data cannot support, and shows its working.

0

Share this prompt

Free — no card needed

Create a free account

to open Data Analysis Agent System Prompt — and the other 364 prompts across 21 categories.

We store your email address to send these. We never sell it or pass it to advertisers. Withdraw at any time. Privacy Policy.

Already have an account?

CategoryAI AgentsForAnalysts, Developers, OperatorsTested onClaudeChatGPTGemini

Running it, start to finish

  1. Describe the data, including what one row represents.
  2. Run all three test questions before relying on it.
  3. Check the assumptions section on the first few real answers.

What you get back

The output this produces, every time.

  • Runs data quality checks before every analysis and stops when one fails.
  • Refuses causal claims the data cannot support, which is where analyses usually mislead.
  • Reports sample sizes per figure, flagging cuts too small to conclude from.

Getting better results

Where this usually goes wrong, and how to avoid it.

  • Describe the data's grain. What one row represents determines whether any aggregate is correct, and it is the thing most often left unstated.
  • Run the causation test question. It checks the one instruction that most often gets ignored under the pressure to give a clean answer.
  • Keep the show-your-working rule. An answer that cannot be checked has to be trusted, and analysis is exactly where trust should not be required.

More AI Agents prompts

All AI Agents

Written for The AI University. Every prompt in this library is original work — authored, tested and revised here, not collected from elsewhere. 365 of them, free with an account.